def find_lines(emotion: str, rhyming_partials: List[Dict]):
"""
Creates combinations of ending lines (3rd and 4th) from some knowledgebase.
"""
data = read_json_file("data/bible_kjv_wrangled.json")
keys, last_words_of_sentences = extract_keys_sentences_last_words(data)
if DEBUG:
print(
f'\nchoose_lines,\n\tkeys length {len(keys)}'
f'\n\n\tlength last words of sentences {len(last_words_of_sentences)}'
)
ret = []
for partial in rhyming_partials:
for word in partial['rhymes']:
rhyming_sentences = []
indices = [
i for i, x in enumerate(last_words_of_sentences) if x == word
]
if indices:
for ix in indices:
rhyming_sentences.append(keys[ix])
if DEBUG:
print(f'rhyming sentences in choose lines {rhyming_sentences}')
for generated_partial in generate_partials(data, partial,
rhyming_sentences):
ret.append(generated_partial)
return ret
def train_model():
data = read_json_file("data/bible_kjv_wrangled.json")
sentences = list(data.values())
# Do we want everything in lowercase?
sentences = [s.lower() for s in sentences]
print("-----------Tokenize corpus-------------")
tokenized_sentences = []
for s in sentences:
tokens = nltk.word_tokenize(s)
tokenized_sentences.append(tokens)
for s in abc.sents():
s = list(filter(lambda x: x.isalpha() and len(x) > 1, s))
s = [x.lower() for x in s] # Do we want everything in lowercase?
tokenized_sentences.append(s)
for s in brown.sents():
s = list(filter(lambda x: x.isalpha() and len(x) > 1, s))
s = [x.lower() for x in s] # Do we want everything in lowercase?
tokenized_sentences.append(s)
print("------------TRAINING FASTTEXT-----------")
model = FastText(tokenized_sentences,
size=100,
window=5,
min_count=5,
workers=4,
sg=1)
print("----------------DONE-------------")
return model
def find_lines(emotion: str, rhyming_partials: List[Dict]):
"""
Creates combinations of ending lines (3rd and 4th) from some knowledgebase.
"""
data = read_json_file("data/bible_kjv_wrangled.json")
# There probably is a better/faster way to do this using dictionaries but I dont know how rn
keys = []
sentences = []
last_word_of_sentences = []
for key, value in data.items():
keys.append(key)
sentences.append(value)
last_word_of_sentence = value.translate(str.maketrans('', '', string.punctuation))
last_word_of_sentence = last_word_of_sentence.strip().split(' ')[-1]
last_word_of_sentences.append(last_word_of_sentence.lower())
ret = []
for partial in rhyming_partials:
for word in partial['rhymes']:
rhyming_sentences = []
indices = [i for i, x in enumerate(last_word_of_sentences) if x == word]
if indices:
for ix in indices:
rhyming_sentences.append(keys[ix])
third = data[random.choice(list(data))]
# selects rhyming sentence if there is at least one, else select random sentence as before
if rhyming_sentences:
fourth = data[random.choice(rhyming_sentences)]
else:
continue
new_partial = partial.copy()
new_partial['rest'] = (third, fourth)
ret.append(new_partial)
return ret
should be a dictionary holding at least 'evaluation' keyword with float value.
"""
print("Group Roses create with input args: {} {}".format(
emotion, word_pairs))
poems = self.evaluate(emotion, word_pairs,
self.generate(emotion, word_pairs))
poems.sort(key=lambda x: x[1])
return list(
map(lambda x: ('\n'.join(x[0]), {
'evaluation': x[1]
}), poems[0:number_of_artifacts]))
if __name__ == '__main__':
poem_creator = PoemCreator()
parser = argparse.ArgumentParser()
parser.add_argument('emotion', help='Emotion for poem.')
parser.add_argument('word_pairs',
help='File for word pairs. Json list of lists')
parser.add_argument('num_poems',
help='Number of poems to output.',
type=int)
args = parser.parse_args()
word_pairs = read_json_file(DATA_FOLDER + args.word_pairs)
word_pairs = [tuple(word_pair) for word_pair in word_pairs]
for poem in poem_creator.create(args.emotion, [('human', 'boss'),
('animal', 'legged')],
args.num_poems):
print(f'----Poem evaluated {poem[1]}\n{poem[0]}\n----')